Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    concepts and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DEPENDENCIA
    0.50
    alumno
    0.46
    graduate
    0.46
     schoolchildren
    0.45
     юни
    0.45
    經典
    0.45
     существу
    0.45
     экземпля
    0.45
    UNCH
    0.44
     유엔
    0.44
    POSITIVE LOGITS
    ان
    0.48
    د
    0.47
     at
    0.46
    Inf
    0.46
    Civ
    0.46
    Lore
    0.46
    Ment
    0.45
    Lot
    0.45
    ;
    0.44
    يب
    0.43
    Act Density 0.003%

    No Known Activations